From 3609786b28b09bf33b3dd396b9bb413ac5bfb9aa Mon Sep 17 00:00:00 2001
From: Eric Wong <e@80x24.org>
Date: Wed, 5 Mar 2025 07:18:32 +0000
Subject: [PATCH] search: make `d:' search prefix consistently date-only

While `d:' previously treated YYYYMMDD and YYYY-MM-DD as
low-precision by assuming 00:00:00 for the HH:MM:SS portion, it
would not do so for dates passed to git-rev-parse (e.g.
"last.year") since the HH:MM:SS of the current time would be
used by git.  So stop remapping `d:' in queries to `dt:' and
continue using `d:' in the YYYYMMDD column.

This does break things like `d:2.hours.ago..' by causing too
many (or too few) results to be returned due to lack of
precision, but I expect small time ranges of less than one
day to be of limited use.

`dt:' remains a higher-precision field for searching on both
date and time from the Date: header, while `d:' is now always
date-only.
---
 lib/PublicInbox/Search.pm | 25 ++++++++++++++++---------
 t/search.t                | 25 +++++++++++--------------
 2 files changed, 27 insertions(+), 23 deletions(-)

diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index 52e1f3356..4773808d5 100644
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -341,16 +341,23 @@ sub date_parse_prepare {
 
 	# expand "dt:2010-10-02" => "dt:2010-10-02..2010-10-03" and like
 	# n.b. git doesn't do YYYYMMDD w/o '-', it needs YYYY-MM-DD
-	# We upgrade "d:" to "dt:" unconditionally
 	if ($pfx eq 'd') {
-		$pfx = 'dt';
-		# upgrade YYYYMMDD to YYYYMMDDHHMMSS
-		$_ .= ' 00:00:00' for (grep(m!\A[0-9]{4}[^[:alnum:]]
-					[0-9]{2}[^[:alnum:]]
-					[0-9]{2}\z!x, @r));
-		$_ .= '000000' for (grep(m!\A[0-9]{8}\z!, @r));
-	}
-	if ($pfx eq 'dt') {
+		if (!defined($r[1])) { # git needs gaps and not /\d{14}/
+			if ($r[0] =~ /\A([0-9]{4})([0-9]{2})([0-9]{2})\z/) {
+				push @$to_parse, "$1-$2-$3 00:00:00";
+			} else {
+				push @$to_parse, $r[0];
+			}
+			$r[0] = "\0%Y%m%d$#$to_parse\0";
+			$r[1] = "\0%Y%m%d+\0";
+		} else {
+			for (@r) {
+				next if $_ eq '' || /\A[0-9]{8}\z/;
+				push @$to_parse, $_;
+				$_ = "\0%Y%m%d$#$to_parse\0";
+			}
+		}
+	} elsif ($pfx eq 'dt') {
 		if (!defined($r[1])) { # git needs gaps and not /\d{14}/
 			if ($r[0] =~ /\A([0-9]{4})([0-9]{2})([0-9]{2})
 					([0-9]{2})([0-9]{2})([0-9]{2})\z/x) {
diff --git a/t/search.t b/t/search.t
index a0f257699..e793f55b1 100644
--- a/t/search.t
+++ b/t/search.t
@@ -584,13 +584,10 @@ SKIP: {
 		skip 'too close to midnight, time is tricky', 6;
 	}
 	$q = $s->query_argv_to_string($g, [qw(d:20101002 blah)]);
-	is($q, 'dt:20101002000000..20101003000000 blah',
-		'YYYYMMDD expanded to range');
+	is $q, 'd:20101002..20101003 blah', 'YYYYMMDD expanded to range';
 	$q = $s->query_argv_to_string($g, [qw(d:2010-10-02)]);
-	is($q, 'dt:20101002000000..20101003000000',
-		'YYYY-MM-DD expanded to range');
+	is $q, 'd:20101002..20101003', 'YYYY-MM-DD expanded to range';
 	$q = $s->query_argv_to_string($g, [qw(rt:2010-10-02.. yy)]);
-	diag "q=$q";
 	$q =~ /\Art:(\d+)\.\. yy/ or fail("rt: expansion failed: $q");
 	is(strftime('%Y-%m-%d', gmtime($1//0)), '2010-10-02', 'rt: beg expand');
 	$q = $s->query_argv_to_string($g, [qw(rt:..2010-10-02 zz)]);
@@ -637,8 +634,8 @@ SKIP: {
 
 	$orig = $qs = qq[f:bob "hello world" d:1993-10-02..2010-10-02];
 	$s->query_approxidate($g, $qs);
-	is($qs, qq[f:bob "hello world" dt:19931002000000..20101002000000],
-		'post-phrase date corrected');
+	is $qs, qq[f:bob "hello world" d:19931002..20101002],
+		'post-phrase date corrected';
 
 	# Xapian uses "" to escape " inside phrases, we don't explictly
 	# handle that, but are able to pass the result through unchanged
@@ -649,28 +646,28 @@ SKIP: {
 		is($qs, $orig, 'phrases unchanged \x'.ord($x).'-\x'.ord($y));
 
 		$s->query_approxidate($g, my $tmp = "$qs d:..2010-10-02");
-		is($tmp, "$orig dt:..20101002000000",
-			'two phrases did not throw off date parsing');
+		is $tmp, "$orig d:..20101002",
+			'two phrases did not throw off date parsing';
 
 		$orig = $qs = qq[${x}hello d:1993-10-02..$y$x world$y];
 		$s->query_approxidate($g, $qs);
 		is($qs, $orig, 'phrases unchanged \x'.ord($x).'-\x'.ord($y));
 
 		$s->query_approxidate($g, $tmp = "$qs d:..2010-10-02");
-		is($tmp, "$orig dt:..20101002000000",
-			'two phrases did not throw off date parsing');
+		is $tmp, "$orig d:..20101002",
+			'two phrases did not throw off date parsing';
 	}
 
 	my $x_days_ago = strftime('%Y%m%d', gmtime(time - (5 * 86400)));
 	$orig = $qs = qq[broken d:5.days.ago..];
 	$s->query_approxidate($g, $qs);
-	like($qs, qr/\Abroken dt:$x_days_ago[0-9]{6}\.\./,
+	like($qs, qr/\Abroken d:$x_days_ago\.\./,
 		'date.phrase.with.dots');
 
 	$orig = $qs = 'd:20101002..now';
 	$s->query_approxidate($g, $qs);
-	like($qs, qr/\Adt:20101002000000\.\.[0-9]{14}\z/,
-		'approxidate on range-end only');
+	like $qs, qr/\Ad:20101002\.\.[0-9]{8}\z/,
+		'approxidate on range-end only';
 
 	$ENV{TEST_EXPENSIVE} or
 		skip 'TEST_EXPENSIVE not set for argv overflow check', 1;
-- 
2.47.3